Online identity reputation

Patent metadata

Field	Value
Publication number	US-10735401-B2
Application number	US-201615266984-A
Country	US
Kind code	B2
Filing date	Sep 15, 2016
Priority date	Sep 15, 2016
Publication date	Aug 4, 2020
Grant date	Aug 4, 2020

Abstract

Examples of the present disclosure describe systems and methods of determining online identity reputation. In aspects, an online identity of an entity may engage in online interactions. The content provided by the online identity may be accessed and analyzed to determine interaction characteristics and reputation metrics for the online identity. Based on the reputation metrics, the online identity and/or entity (and content therefrom) may be filtered from further online interactions. In some aspects, interaction data may be stored in a data store. An interaction mapping component having access to the data store may analyze the data store data to determine mappings between online identities, entities and interactions. In at least one aspect, an opt-in certificate system may also be provided. The opt-in system may provide an online identity or entity a certificate to securely validate identity.

First claim

What is claimed is:

1. A system comprising:
at least a first processor; and
a first memory coupled to the at least a first processor, the first memory comprising computer executable instructions that, when executed by the at least a first processor, performs a method for determining online identity reputation, the method comprising:
receiving interaction content for an online identity associated with an interaction, wherein the online identity identifies a user who is party to the interaction and receiving the interaction content comprises determining navigated content and recording one or more portions of the navigated content by identifying user feedback signals comprising at least one of screen swipes, clicks, scrolls, cursor movement, dwell time, session duration, query (re)formulation statistics, element visibility, and occlusion events;
analyzing the interaction content and the navigated content to determine one or more content characteristics and one or more interaction characteristics;
generating a feature vector for the interaction content based upon the one or more content characteristics and the one or more interaction characteristics;
determining a set of reputation metrics for the interaction based upon the feature vector, wherein determining the reputation metrics comprises:
parsing the feature vector to extract features of the interaction; and
comparing features of the interaction with past interaction features associated with the online identity; and

updating a preexisting reputation score for the online identity based upon the set of reputation metrics for the interaction.

2. The system of claim 1 , wherein the interaction content corresponds to content provided by the online identity during one or more online interactions.

3. The system of claim 1 , wherein analyzing the interaction content comprises:
parsing the received interaction content in real-time to generate a first set of data;
providing the first set of data to one or more statistical models; and
using the one or more statistical models to generate at least a first portion of the one or more interaction characteristics based on the first set of data.

4. The system of claim 3 , wherein analyzing the interaction content further comprises:
accessing a knowledge base including user data corresponding to the online identity;
using the user data to determine a second set of data;
providing the second set of data to the one or more statistical models; and
using the one or more statistical models to generate a second portion of the one or more interaction characteristics based on the second set of data.

5. The system of claim 4 , wherein the first portion of the one or more interaction characteristics and the second portion of the one or more interaction characteristics are used to generate one or more feature vectors.

6. The system of claim 1 , wherein the one or more interaction characteristics comprise at least one of content attributes, interaction attributes, dialogue attributes, behavioral attributes, demographic attributes, and environmental attributes.

7. The system of claim 1 , wherein determining the set of reputation metrics comprises:
providing the one or more interaction characteristics to a predictive model; and
using the predictive model to generate the set of reputation metrics, wherein the reputation metrics correspond to at least one of a reputation and a trustworthiness of the online identity.

8. The system of claim 1 , further comprising: using the set of reputation metrics to generate a set of policy controls, wherein the set of policy controls is associated with a set of boundaries for interacting with the online identity.

9. The system of claim 8 , wherein generating the set of policy controls comprises using at least one of a rule set and a machine learning mechanism to modify preexisting reputation metrics in accordance with the set of reputation metrics.

10. A method comprising:
receiving interaction content for an online identity associated with an interaction, wherein the online identity identifies a user who is party to the interaction and receiving the interaction content comprises determining navigated content and recording one or more portions of the navigated content by identifying user feedback signals comprising at least one of screen swipes, clicks, scrolls, cursor movement, dwell time, session duration, query (re)formulation statistics, element visibility, and occlusion events;
analyzing the interaction content and the navigated content to determine one or more content characteristics and one or more interaction characteristics;
generating a feature vector for the interaction content based upon the one or more content characteristics and the one or more interaction characteristics;
determining a set of reputation metrics for the interaction based upon the feature vector, wherein determining the reputation metrics comprises:
parsing the feature vector to extract features of the interaction; and
comparing features of the interaction with past interaction features associated with the online identity; and

updating a preexisting reputation score for the online identity based upon the set of reputation metrics for the interaction.

11. The method of claim 10 , wherein the interaction content corresponds to content provided by the online identity during one or more online interactions.

12. The method of claim 10 , wherein analyzing the interaction content comprises:
parsing the received interaction content in real-time to generate a first set of data;
providing the first set of data to one or more statistical models; and
using the one or more statistical models to generate at least a first portion of the one or more interaction characteristics based on the first set of data.

13. The method of claim 12 , wherein analyzing the interaction content further comprises:
accessing a knowledge base including user data corresponding to the online identity;
using the user data to determine a second set of data;
providing the second set of data to the one or more statistical models; and
using the one or more statistical models to generate a second portion of the one or more interaction characteristics based on the second set of data.

14. The method of claim 13 , wherein the first portion of the one or more interaction characteristics and the second portion of the one or more interaction characteristics are used to generate one or more feature vectors.

15. The method of claim 10 , wherein the one or more interaction characteristics comprise at least one of content attributes, interaction attributes, dialogue attributes, behavioral attributes, demographic attributes, and environmental attributes.

16. The method of claim 10 , wherein determining the set of reputation metrics comprises:
providing the one or more interaction characteristics to a predictive model; and
using the predictive model to generate the set of reputation metrics, wherein the reputation metrics correspond to at least one of a reputation and a trustworthiness of the online identity.

17. The method of claim 10 , further comprising: using the set of reputation metrics to generate a set of policy controls, wherein the set of policy controls is associated with a set of boundaries for interacting with the online identity.

18. The method of claim 17 , wherein generating the set of policy controls comprises using at least one of a rule set and a machine learning mechanism to modify preexisting reputation metrics in accordance with the set of reputation metrics.

Assignees

• Webroot Inc

Inventors

• Lonas Hal

Classifications

• G06F21/60

  Protecting data · CPC title

• H04L63/0823 Primary

  using certificates (cryptographic mechanisms or cryptographic arrangements for entity authentication involving certificates H04L9/3263) · CPC title

• B66B11/0407

  actuated by an electrical linear motor (in the counterweight B66B17/12) · CPC title

• B66B9/003

  for lateral transfer of car or frame, e.g. between vertical hoistways or to/from a parking position · CPC title

• B66B7/025

  End supports, i.e. at top or bottom · CPC title